AIML Сontent Moderation
PassAudited by ClawScan on May 1, 2026.
Overview
This is a straightforward AIMLAPI content-moderation helper, but it sends checked text to an external provider using your API key.
This appears safe to install for text moderation if you are comfortable sending checked text to AIMLAPI. Use a dedicated API key, avoid submitting sensitive content unless permitted by your policies, and do not rely on it for image moderation based on the provided artifacts.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The skill can use your AIMLAPI account key for moderation API calls.
The script reads an AIMLAPI API key from the environment and uses it as a bearer token for the provider request.
api_key = os.getenv("AIMLAPI_API_KEY") ... "Authorization": f"Bearer {api_key}"Use a dedicated AIMLAPI key if possible, keep it out of logs and shared shells, and rotate it if exposed.
Any text submitted for moderation may be processed by the external AIMLAPI service.
The text being checked is sent to an external AIMLAPI endpoint as chat-completion content.
url = "https://api.aimlapi.com/v1/chat/completions" ... "messages": [{"role": "user", "content": content}]Do not submit sensitive or regulated content unless AIMLAPI's data handling terms are acceptable for your use case.
You have less external context for verifying the publisher or tracking upstream changes.
The registry information does not provide a source repository or homepage for provenance review.
Source: unknown; Homepage: none
Review the included files before installing and prefer versions with clear source provenance when available.
Users may expect image moderation support that is not evidenced by the included implementation.
The implementation exposes a text-only input path, while the skill description advertises text or image classification.
parser.add_argument("--content", required=True, help="Text to check for safety")Treat this skill as text-only unless image-handling artifacts are added and reviewed.